The company will also create companion software to make the technology easier for future users. To expand its chip technology, Luminous will work with photonics designers and other specialists. The business will quadruple its technical staff thanks to its most recent $105 million fundraising round. According to Luminous, their technology will make it simpler to deliver the expanding computing capacity required for the advancement of AI. Due to the increasing complexity of AI models, this presents difficulties: According to OpenAI, between 20, the computing power needed for the biggest AI training runs increased every three and a half months. The more hardware is needed to train a neural network, the more complicated it is. The search engine giant utilizes the chips to power internal apps and makes them available through its public cloud. To execute AI models, Google LLC designed TPUs, specialized semiconductors. Luminous Computing raised 105M in a Series A round, with participation from investors including Gigafund, Bill Gates, 8090 Partners, Neo, Third Kind Venture Capital, Alumni Ventures Group, Strawberry Creek Ventures, Horsley Bridge, Modern Venture Partners, among others. Luminous wants to create a silicon photonics device that performs 3,000 times better than a third-generation Tensor Processing Unit, or TPU, circuit board. The business did, however, disclose its development objectives in conjunction with today’s investment release. That is the goal that Luminous is attempting to achieve.įew technical information concerning Luminous technique has so far been disclosed. The idea behind silicon photonics is to make use of the fact that light moves more swiftly to carry out computations than is feasible with a conventional processor in which data is encoded as electricity. In some cases, light may move far more quickly than electricity. A distinct method is used by silicon photonics technology, which encodes data as light instead of electricity. To do computations, the processor manipulates this electricity, such as by transferring it between transistors. The information processed by a conventional processor is stored as electricity. Luminous Computing, the machine learning systems company building the world’s most powerful AI supercomputers, today announced the appointment of Michael Hochberg as President, where he is running engineering and operations. Based on silicon photonics, the supercomputer can considerably accelerate some processing workloads. Bill Gates, Gigafund, 8090 Partners, Neo, Third Kind Venture Capital, Alumni Ventures Group, Strawberry Creek Ventures, Horsley Bridge, Modern Venture Partners, and others were among the contributors.īased in Mountain View, California, the supercomputer being built by Luminous will run AI models. There were more than six investors who took part in the Series A financing. Luminous Computing Inc., a startup creating a novel class of supercomputers for running AI models, said today that it has completed a $105 million investment round.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |